Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1377 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 4.6101. Min Range: -4.6101
Max Act: 4.6101. Min Act: -0.1700
Data Index: 777467 (C4 (Web Text))
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6101. Min Range: -4.6101
Max Act: 4.4851. Min Act: -0.1700
Data Index: 1067573 (C4 (Web Text))
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6101. Min Range: -4.6101
Max Act: 4.3914. Min Act: -0.1700
Data Index: 1316127 (C4 (Web Text))
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6101. Min Range: -4.6101
Max Act: 4.3289. Min Act: -0.1700
Data Index: 193518 (C4 (Web Text))
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6101. Min Range: -4.6101
Max Act: 4.3601. Min Act: -0.1700
Data Index: 142648 (C4 (Web Text))
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6101. Min Range: -4.6101
Max Act: 4.3601. Min Act: -0.1700
Data Index: 372146 (C4 (Web Text))
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6101. Min Range: -4.6101
Max Act: 4.3601. Min Act: -0.1700
Data Index: 174845 (C4 (Web Text))
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6101. Min Range: -4.6101
Max Act: 4.2351. Min Act: -0.1700
Data Index: 773450 (C4 (Web Text))
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6101. Min Range: -4.6101
Max Act: 4.3289. Min Act: -0.1700
Data Index: 938989 (C4 (Web Text))
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6101. Min Range: -4.6101
Max Act: 4.3289. Min Act: -0.1700
Data Index: 977543 (C4 (Web Text))
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6101. Min Range: -4.6101
Max Act: 4.2663. Min Act: -0.1700
Data Index: 679743 (C4 (Web Text))
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6101. Min Range: -4.6101
Max Act: 4.2976. Min Act: -0.1700
Data Index: 716765 (C4 (Web Text))
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6101. Min Range: -4.6101
Max Act: 4.2976. Min Act: -0.1700
Data Index: 651698 (C4 (Web Text))
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6101. Min Range: -4.6101
Max Act: 4.2351. Min Act: -0.1700
Data Index: 649215 (C4 (Web Text))
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6101. Min Range: -4.6101
Max Act: 4.2663. Min Act: -0.1700
Data Index: 1326637 (C4 (Web Text))
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6101. Min Range: -4.6101
Max Act: 4.2663. Min Act: -0.1700
Data Index: 1266504 (C4 (Web Text))
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6101. Min Range: -4.6101
Max Act: 4.2663. Min Act: -0.1700
Data Index: 869555 (C4 (Web Text))
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6101. Min Range: -4.6101
Max Act: 4.2976. Min Act: -0.1700
Data Index: 331034 (C4 (Web Text))
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6101. Min Range: -4.6101
Max Act: 4.2351. Min Act: -0.1700
Data Index: 387711 (C4 (Web Text))
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6101. Min Range: -4.6101
Max Act: 4.2663. Min Act: -0.1700
Data Index: 1296778 (C4 (Web Text))
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #19